Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jxoesneon/Ciel --skill ciel-ml-and-data-patternsgit clone --depth 1 https://github.com/jxoesneon/CielWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jxoesneon/ciel/ciel-ml-and-data-patterns)<a href="https://agentmods.dev/skills/jxoesneon/ciel/ciel-ml-and-data-patterns"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/ciel-ml-and-data-patterns/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jxoesneon/ciel/ciel-ml-and-data-patterns"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/ciel-ml-and-data-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.00548 |
| Opus 5 | $0.00012 | $0.00274 |
| Sonnet 5 | $0.00005 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
ciel-ml-and-data-patterns scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
CIEL ADAPTATION: ML & Data (The Intelligence Layer)
This skill manages high-performance data patterns, from deep learning training loops to SQL query optimization.
PyTorch ML Patterns
- Device-Agnostic: ALWAYS use
device = torch.device(...). Prohibit hardcoded.cuda()calls. - Reproducibility: Set seeds for
torch,np, andrandomin a centralset_seed()function. - Shape Integrity: Annotate and verify tensor shapes in the
forward()pass comments. - Efficiency: Use
optimizer.zero_grad(set_to_none=True)andmodel.eval()for validation.
Postgres Data patterns
- Indexing: Equality columns first, then range columns. Use
GINfor JSONB andBRINfor time-series. - Types: Use
bigintfor IDs,timestamptzfor times, andtextfor variable strings. - Pagination: Use keyset/cursor pagination (
WHERE id > $last_id) instead ofOFFSETfor O(1) performance. - Security: Wrap RLS policies in
(SELECT auth.uid()) = user_idfor optimization.
Memory Management
- AMP: Use
torch.amp.GradScalerfor mixed-precision performance. - Checkpointing: Save
model_state_dictANDoptimizer_state_dictto allow resuming training.
Anti-Patterns
- In-place Mutation: Using
x += residualin PyTorch (breaks autograd). Usex = x + residual. - Small Inserts: Performing SQL inserts in a loop instead of batching.
- Select *: Reading every column in SQL (causes unnecessary I/O bloat).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 51 lines · 24 tokens per session scan A 22844ce47f61
ciel-ml-and-data-patterns is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 24 tokens to every session and 548 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cloud-sql-postgres-vectorassist
Use these skills to set up and optimize production-ready vector workloads by simply expressing your intent and performance requirements.
bigquery-ai-ml
Skill for BigQuery AI and Machine Learning queries using standard SQL and AI. functions (preferred over dedicated tools).
pgvector-semantic-search
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…
postgres-hybrid-text-search
Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). Trigger when user asks to: Combine keyword and semantic search Implement hybrid search or multi-modal retrieval Use BM25/pgtextsearch with pgvector together Implement RRF (Reciprocal…
mongodb-atlas-stream-processing
Manages MongoDB Atlas Stream Processing (ASP) workflows. Handles workspace provisioning, data source/sink connections, processor lifecycle operations, debugging diagnostics, and tier sizing. Supports Kafka, Atlas clusters, S3, HTTPS, and Lambda integrations for streaming data workloads and event processing. NOT for…
polar-local-environment
This skill should be used when setting up or managing Polar local development environment with Docker.